Observability Architecture

What it does

When your agent uses it

• Changing metrics
• Log instrumentation
• Debugging health checks
• Wiring Prometheus alert rules

Example prompts

• “/observability-architecture”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

1. 1HTTP metrics — MetricsMiddleware (src/server/middleware/metrics.rs) counts requests with process-local atomics and renders Prometheus text…
2. 2Health/status routes — src/server/routes/health.rs mounts /health, /health/ready, /health/detailed, /status, /version, and /metrics on the…
3. 3Callback exporters — configured under monitoring.callbacks, the OpenTelemetryIntegration (OTLP/HTTP JSON), DataDogIntegration, and…

What it can do on your machine

Read from SKILL.md and the folder at commit ed3f4d9. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are yaml).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Observability Architecture loads about 1.3k tokens when it runs. Until then it costs about 108 tokens; SKILL.md has 302 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~108

When it runs · the whole SKILL.md, loaded when a task matches

~1.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from majiayu000/litellm-rs at commit ed3f4d9, republished under its MIT licence (© majiayu000). 302 words, ~1,262 tokens.

name

observability-architecture

description

LiteLLM-RS Observability Architecture. Covers the Prometheus-format metrics rendered by the metrics middleware and /metrics endpoint, health/readiness endpoints, request logging, and the OpenTelemetry/Datadog/Langfuse callback exporters. Use when adding or changing metrics or log instrumentation, implementing or debugging health checks, wiring Prometheus alert rules, or configuring the monitoring stack.

┌─────────────────────────────────────────────────────────────────┐
│                    LiteLLM Gateway                              │
├─────────────────────────────────────────────────────────────────┤
│  ┌───────────────┐  ┌───────────────┐  ┌───────────────┐       │
│  │  Metrics      │  │ Health/status │  │  Callback     │       │
│  │  middleware   │  │ routes        │  │  dispatcher   │       │
│  └───────┬───────┘  └───────┬───────┘  └───────┬───────┘       │
└──────────┼──────────────────┼──────────────────┼───────────────┘
           ▼                  ▼                  ▼
┌──────────────────┐ ┌──────────────────┐ ┌──────────────────┐
│ Prometheus       │ │ LB / K8s probes  │ │ OTLP / Datadog / │
│ scrapes /metrics │ │ + JSON status    │ │ Langfuse backends│
└──────────────────┘ └──────────────────┘ └──────────────────┘

monitoring:
  metrics:
    enabled: true          # gates MetricsMiddleware (src/server/http.rs)
    port: 9090             # default 9090; validated > 0 when enabled
    path: "/metrics"       # validated non-empty, starts with '/'
    interval_seconds: 15
  tracing:
    enabled: false
    endpoint: null         # REQUIRED when enabled: true (config validation)
    service_name: "litellm-rs"
    sampling_rate: 0.1
    jaeger: null           # or {agent_endpoint, service_name}
  health:
    path: "/health"
    detailed: true
  logging: null            # or {level, format: text|json|structured, outputs}
  callbacks:
    queue_capacity: 1024
    timeout_ms: 5000
    backends: []           # {type: opentelemetry|datadog|langfuse, config: {...}}

© majiayu000, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 5 other files in .claude/skills/observability-architecture of majiayu000/litellm-rs.

• SKILL.md
• reference/alerting.md
• reference/best-practices.md
• reference/health-checks.md
• reference/metrics.md
• reference/tracing-and-logging.md

Open the folder on GitHubat commit ed3f4d9